To cite this version:Anne-Sophie Puthon, Fawzi Nashashibi, Benazouz Bradai. Improvement of multisensor fusion in speed limit determination by quantifying navigation reliability. Intelligent Transportation System Conference -ITSC 10, Sep 2010, Funchal, Portugal. pp.855 -860, 2010, <10.1109/ITSC.2010 .5625242>. Improvement of multisensor fusion in speed limit determination by quantifying navigation reliabilityAnne-Sophie Puthon, Fawzi Nashashibi and Benazouz BradaiAbstract-Speed limit determination is a complex task that may be solved by fusing data from GIS (Geographical Information System) and camera sensor. Among the existing data fusion models the Dempster-Shafer Belief Theory is found to be the most appropriate in this application. A confidence measure weights each source output, namely speed limit present on road sign and driving situation. Using the discounting scheme of Dempster-Shafer, we propose a new way of computing the navigation confidence measure by taking into account the reliability of the GIS. Preliminary tests showed that our method achieves promising results and solves conflicts between visionand navigation-based system.

No abstract

Speed limit determination systems for cars based on vision are more and more developed. Roadsign detection is nowadays a well managed problem. However, in some situations this information is not sufficient to know the speed limitation. Restrictions are sometimes applicable and specified by subsigns. These small rectangles often provide essential information about the applicability scope (vehicle type, condition, lane, etc.) of speed limits. We present an approach of subsign localization based on region growing with an initial step of seed selection using morphological reconstruction. A comparison is also performed with three other techniques based on edge, color and graph on two databases gathering French and German subsigns. The obtained subsign correct detection is above 65%.

Abstract-Traffic Sign Recognition (TSR) is now relatively well-handled by several approaches. However, traffic signs are often completed by one (or several) supplementary placed below. They are essential for correct interpretation of main sign, as they specify its applicability scope. difficulty of supplementary sub-sign recognition potentially infinite number of classes, as nearly any can be written on them. In this paper, we propose and evaluate a hierarchical approach for recognition of supplementary signs, in which the "meta-class" of the sub-sign (Arrow, P Text or Mixed) is first determined. The classification is based on the pyramid-HOG feature, completed by dark area proportion measured on the same pyramid. large database of images with and without supp shows that the classification accuracy of our approach 95% precision and recall. When used on output of our sub specific detection algorithm, the global correct detection and recognition rate is 91%.

Traffic Sign Recognition (TSR) is now relatively well-handled by several approaches. However, traffic signs are often completed by one (or several) supplementary placed below. They are essential for correct interpretation of main sign, as they specify its applicability scope. difficulty of supplementary sub-sign recognition potentially infinite number of classes, as nearly any can be written on them. In this paper, we propose and evaluate a hierarchical approach for recognition of supplementary signs, in which the "meta-class" of the sub-sign (Arrow, P Text or Mixed) is first determined. The classification is based on the pyramid-HOG feature, completed by dark area proportion measured on the same pyramid. large database of images with and without supp shows that the classification accuracy of our approach 95% precision and recall. When used on output of our sub specific detection algorithm, the global correct detection and recognition rate is 91%.